Patrick Henriksen is a PhD candidate in the Verification of Autonomous Systems (VAS) group at Imperial College London. His research concerns developing principled solutions to formal verification, robust training, and repair of neural networks. He leads the development of the VeriNet toolkit, a symbolic interval propagation-based formal verification toolkit for neural networks.
Henriksen P, Lomuscio A, Robust training of neural networks against bias field perturbations, AAAI Conference on Artificial Intelligence (AAAI23), AAAI
Henriksen P, Leofante F, Lomuscio A, 2022, Repairing misclassifications in neural networks using limited data, SAC '22, Pages:1031-1038
et al., Bias Field Robustness Verification of Large Neural Image Classifiers, British Machine Vision Conference (BMVC21)
Henriksen P, Lomuscio A, 2021, DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis, Pages:2549-2555, ISSN:1045-0823
Henriksen P, Lomuscio A, Efficient Neural Network Verification via Adaptive Refinement and Adversarial Search, European Conference on Artificial Intelligence (ECAI20)